Ivan Ruchkin

Ivan Ruchkin is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Florida, where he leads the Trustworthy Engineered Autonomy (TEA) Lab. He holds affiliate appointments in the Department of Mechanical & Aerospace Engineering, Department of Computer & Information Science & Engineering, Nelms Institute for the Connected World, Artificial Intelligence Academic Initiative, and Intelligent Critical Care Center.

Dr. Ruchkin's research focuses on making autonomous systems safer and more trustworthy through novel techniques for modeling, analyzing, verifying, controlling, and monitoring cyber-physical systems. His work spans formal verification methods, safety monitoring with statistical guarantees, model integration approaches, and neuro-symbolic paradigms that combine the strengths of neural networks and symbolic reasoning. He has made significant contributions to the fields of conformal prediction for safety guarantees, neural network repair while preserving correct behaviors, and physically interpretable world models for autonomous systems.

His recent publications reveal a strong trend toward developing statistically sound safety guarantees for learning-enabled systems, with particular emphasis on conformal prediction methods that provide calibrated confidence measures. His work bridges the gap between high-dimensional perception (like vision) and formal safety guarantees, addressing the critical challenge of ensuring safety in systems where traditional verification methods fail due to complexity.

Dr. Ruchkin is actively involved in the academic community as a program committee member for major conferences including ASE 2025 (Research Papers track) and ICSE 2026 (New Ideas and Emerging Results track). His research has been published in top venues across software engineering, formal methods, and robotics.

At the University of Florida, he directs the TEA Lab which focuses on developing theoretically grounded yet practically applicable methods for trustworthy autonomy. His lab investigates approaches that combine formal methods with machine learning to create safety-critical autonomous systems that can provide statistical guarantees about their behavior even in complex, uncertain environments.